Weaviate
An open-source vector database with hybrid search and built-in vectorisation modules.
Weaviate is an open-source vector database that can also handle the embedding step itself: modules call an embedding model on ingest and query, so you can hand it raw text. It has strong hybrid search, combining vector and keyword scoring.
It runs self-hosted or as a managed cloud, and has a sizeable ecosystem of tools and integrations around it.
Where it fits
A fit when you want hybrid search and the option to let the database handle vectorisation for you.
Where it does not fit
A dedicated system to run: unnecessary when pgvector inside your existing Postgres would do.
Alternatives to Weaviate
The closest options on the map, and where each fits instead.
-
Qdrant Dedicated vector database
A strong pick when retrieval needs to combine similarity with metadata filtering, or has outgrown an in-database extension.
-
Milvus Dedicated vector database
A fit when vector search must operate at very large scale, into the billions of vectors.
-
pgvector Embedded vector search
The right call when your data already lives in Postgres and the vector workload is moderate: retrieval without a second database.
Unlike Weaviate No hosted API
-
Elasticsearch Search engine
A fit when you already run Elasticsearch and want hybrid keyword-plus-vector search in the system you operate.
Unlike Weaviate Source availableMaturity: mature
Pairs with
Commonly used alongside it.
